R3SGM: Real-time raster-respecting semi-global matching for power-constrained systems
Stereo depth estimation is used for many computer vision applications. Though many popular methods strive solely for depth quality, for real-time mobile applications (e.g. prosthetic glasses or micro-UAVs), speed and power efficiency are equally, if not more, important. Many real-world systems rely...
Main Authors: | , , , , |
---|---|
Format: | Conference item |
Published: |
Institute for Electrical and Electronics Engineers
2019
|
_version_ | 1797084969528459264 |
---|---|
author | Rahnama, O Cavallari, T Golodetz, S Walker, S Torr, P |
author_facet | Rahnama, O Cavallari, T Golodetz, S Walker, S Torr, P |
author_sort | Rahnama, O |
collection | OXFORD |
description | Stereo depth estimation is used for many computer vision applications. Though many popular methods strive solely for depth quality, for real-time mobile applications (e.g. prosthetic glasses or micro-UAVs), speed and power efficiency are equally, if not more, important. Many real-world systems rely on Semi-Global Matching (SGM) to achieve a good accuracy vs. speed balance, but power efficiency is hard to achieve with conventional hardware, making the use of embedded devices such as FPGAs attractive for low-power applications. However, the full SGM algorithm is ill-suited to deployment on FPGAs, and so most FPGA variants of it are partial, at the expense of accuracy. In a non-FPGA context, the accuracy of SGM has been improved by More Global Matching (MGM), which also helps tackle the streaking artifacts that afflict SGM. In this paper, we propose a novel, resource-efficient method that is inspired by MGM's techniques for improving depth quality, but which can be implemented to run in real time on a low-power FPGA. Through evaluation on multiple datasets (KITTI and Middlebury), we show that in comparison to other real-time capable stereo approaches, we can achieve a state-of-the-art balance between accuracy, power efficiency and speed, making our approach highly desirable for use in real-time systems with limited power. |
first_indexed | 2024-03-07T02:02:33Z |
format | Conference item |
id | oxford-uuid:9ddae05f-d32c-4e6f-9d31-95f166a3c1fb |
institution | University of Oxford |
last_indexed | 2024-03-07T02:02:33Z |
publishDate | 2019 |
publisher | Institute for Electrical and Electronics Engineers |
record_format | dspace |
spelling | oxford-uuid:9ddae05f-d32c-4e6f-9d31-95f166a3c1fb2022-03-27T00:46:08ZR3SGM: Real-time raster-respecting semi-global matching for power-constrained systemsConference itemhttp://purl.org/coar/resource_type/c_5794uuid:9ddae05f-d32c-4e6f-9d31-95f166a3c1fbSymplectic Elements at OxfordInstitute for Electrical and Electronics Engineers2019Rahnama, OCavallari, TGolodetz, SWalker, STorr, PStereo depth estimation is used for many computer vision applications. Though many popular methods strive solely for depth quality, for real-time mobile applications (e.g. prosthetic glasses or micro-UAVs), speed and power efficiency are equally, if not more, important. Many real-world systems rely on Semi-Global Matching (SGM) to achieve a good accuracy vs. speed balance, but power efficiency is hard to achieve with conventional hardware, making the use of embedded devices such as FPGAs attractive for low-power applications. However, the full SGM algorithm is ill-suited to deployment on FPGAs, and so most FPGA variants of it are partial, at the expense of accuracy. In a non-FPGA context, the accuracy of SGM has been improved by More Global Matching (MGM), which also helps tackle the streaking artifacts that afflict SGM. In this paper, we propose a novel, resource-efficient method that is inspired by MGM's techniques for improving depth quality, but which can be implemented to run in real time on a low-power FPGA. Through evaluation on multiple datasets (KITTI and Middlebury), we show that in comparison to other real-time capable stereo approaches, we can achieve a state-of-the-art balance between accuracy, power efficiency and speed, making our approach highly desirable for use in real-time systems with limited power. |
spellingShingle | Rahnama, O Cavallari, T Golodetz, S Walker, S Torr, P R3SGM: Real-time raster-respecting semi-global matching for power-constrained systems |
title | R3SGM: Real-time raster-respecting semi-global matching for power-constrained systems |
title_full | R3SGM: Real-time raster-respecting semi-global matching for power-constrained systems |
title_fullStr | R3SGM: Real-time raster-respecting semi-global matching for power-constrained systems |
title_full_unstemmed | R3SGM: Real-time raster-respecting semi-global matching for power-constrained systems |
title_short | R3SGM: Real-time raster-respecting semi-global matching for power-constrained systems |
title_sort | r3sgm real time raster respecting semi global matching for power constrained systems |
work_keys_str_mv | AT rahnamao r3sgmrealtimerasterrespectingsemiglobalmatchingforpowerconstrainedsystems AT cavallarit r3sgmrealtimerasterrespectingsemiglobalmatchingforpowerconstrainedsystems AT golodetzs r3sgmrealtimerasterrespectingsemiglobalmatchingforpowerconstrainedsystems AT walkers r3sgmrealtimerasterrespectingsemiglobalmatchingforpowerconstrainedsystems AT torrp r3sgmrealtimerasterrespectingsemiglobalmatchingforpowerconstrainedsystems |